BaCO: A Fast and Portable Bayesian Compiler Optimization Framework
Lund University
arXiv:2212.11142 [cs.PL], (1 Dec 2022)
@misc{https://doi.org/10.48550/arxiv.2212.11142,
doi={10.48550/ARXIV.2212.11142},
url={https://arxiv.org/abs/2212.11142},
author={Hellsten, Erik and Souza, Artur and Lenfers, Johannes and Lacouture, Rubens and Hsu, Olivia and Ejjeh, Adel and Kjolstad, Fredrik and Steuwer, Michel and Olukotun, Kunle and Nardi, Luigi},
keywords={Programming Languages (cs.PL), Machine Learning (cs.LG), Performance (cs.PF), FOS: Computer and information sciences, FOS: Computer and information sciences},
title={BaCO: A Fast and Portable Bayesian Compiler Optimization Framework},
publisher={arXiv},
year={2022},
copyright={Creative Commons Attribution 4.0 International}
}
We introduce the Bayesian Compiler Optimization framework (BaCO), a general purpose autotuner for modern compilers targeting CPUs, GPUs, and FPGAs. BaCO provides the flexibility needed to handle the requirements of modern autotuning tasks. Particularly, it deals with permutation, ordered, and continuous parameter types along with both known and unknown parameter constraints. To reason about these parameter types and efficiently deliver high-quality code, BaCO uses Bayesian optimization algorithms specialized towards the autotuning domain. We demonstrate BaCO’s effectiveness on three modern compiler systems: TACO, RISE & ELEVATE, and HPVM2FPGA for CPUs, GPUs, and FPGAs respectively. For these domains, BaCO outperforms current state-of-the-art autotuners by delivering on average 1.39x-1.89x faster code with a tiny search budget, and BaCO is able to reach expert-level performance 2.89x-8.77x faster.
January 8, 2023 by hgpu
